Dev Builds » 20240513-0530

Use this dev build

NCM plays each Stockfish dev build 20,000 times against Stockfish 15. This yields an approximate Elo difference and establishes confidence in the strength of the dev builds.

Summary

Host Duration Avg Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo
ncm-dbt-01 06:50:53 584279 4008 1509 644 1855 +76.18 ± 4.99 0 132 889 969 14 +157.51 ± 11.39
ncm-dbt-02 06:51:07 587891 4032 1473 594 1965 +76.98 ± 5.03 1 134 883 981 17 +158.96 ± 11.43
ncm-dbt-03 06:49:24 587302 4000 1483 584 1933 +79.44 ± 5.11 4 127 855 994 20 +164.72 ± 11.63
ncm-dbt-04 06:49:53 571823 4000 1430 576 1994 +75.34 ± 5.04 1 135 890 957 17 +155.12 ± 11.38
ncm-dbt-05 06:50:11 586187 3960 1439 602 1919 +74.56 ± 5.02 2 125 903 934 16 +153.72 ± 11.28
20000 7334 3000 9666 +76.5 ± 2.25 8 653 4420 4835 84 +158.0 ± 5.11

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
384008 ncm-dbt-01 584537 8 3 1 4 +88.62 ± 93.84 0 0 2 2 0 +190.67 ± 458.56
384007 ncm-dbt-02 588004 32 11 4 17 +77.24 ± 55.01 0 1 7 8 0 +162.99 ± 139.28
384006 ncm-dbt-05 588728 460 153 64 243 +68.08 ± 14.65 1 15 108 106 0 +143.61 ± 32.71
384005 ncm-dbt-04 572235 500 185 72 243 +79.9 ± 14.07 0 14 112 121 3 +164.07 ± 32.12
384004 ncm-dbt-03 589240 500 178 70 252 +76.25 ± 14.67 0 19 107 121 3 +155.54 ± 33.04
384003 ncm-dbt-01 585379 500 193 88 219 +74.06 ± 14.46 0 19 109 120 2 +152.18 ± 32.72
384002 ncm-dbt-02 585295 500 187 83 230 +73.34 ± 14.72 1 19 106 123 1 +153.86 ± 33.21
384001 ncm-dbt-05 587325 500 185 85 230 +70.43 ± 13.76 0 16 119 114 1 +145.54 ± 31.07
384000 ncm-dbt-03 586477 500 180 76 244 +73.34 ± 15.52 4 15 106 123 2 +157.24 ± 33.21
383999 ncm-dbt-04 571471 500 187 55 258 +93.95 ± 13.13 0 6 109 132 3 +198.34 ± 32.19
383998 ncm-dbt-01 584664 500 187 88 225 +69.71 ± 14.31 0 21 109 120 0 +145.54 ± 32.74
383997 ncm-dbt-02 585421 500 186 69 245 +82.83 ± 13.85 0 13 109 126 2 +172.78 ± 32.58
383996 ncm-dbt-05 580240 500 182 76 242 +74.79 ± 13.62 0 14 117 118 1 +155.54 ± 31.31
383995 ncm-dbt-03 586901 500 181 77 242 +73.33 ± 14.3 0 18 112 118 2 +150.51 ± 32.22
383994 ncm-dbt-01 584706 500 192 69 239 +87.26 ± 13.95 0 14 100 135 1 +185.33 ± 34.19
383993 ncm-dbt-04 571873 500 172 84 244 +61.79 ± 14.55 0 23 118 107 2 +124.6 ± 31.38
383992 ncm-dbt-02 588984 500 174 73 253 +71.16 ± 14.64 0 21 109 118 2 +145.54 ± 32.74
383991 ncm-dbt-05 585632 500 192 73 235 +84.3 ± 14.18 0 13 109 124 4 +172.78 ± 32.58
383990 ncm-dbt-01 581527 500 185 81 234 +73.33 ± 14.15 0 17 114 117 2 +150.51 ± 31.88
383989 ncm-dbt-03 587877 500 192 76 232 +82.1 ± 14.56 0 17 103 127 3 +169.27 ± 33.7
383988 ncm-dbt-04 572195 500 171 63 266 +76.25 ± 14.95 0 20 106 120 4 +153.86 ± 33.21
383987 ncm-dbt-02 589112 500 187 72 241 +81.36 ± 13.66 0 10 119 117 4 +165.8 ± 30.8
383986 ncm-dbt-05 585042 500 185 72 243 +79.9 ± 13.92 0 15 108 126 1 +167.53 ± 32.81
383985 ncm-dbt-01 584243 500 193 85 222 +76.25 ± 14.1 0 15 115 117 3 +155.54 ± 31.67
383984 ncm-dbt-03 588387 500 188 69 243 +84.3 ± 13.11 0 9 114 126 1 +178.11 ± 31.55
383983 ncm-dbt-02 587749 500 180 74 246 +74.79 ± 13.76 0 13 121 113 3 +152.18 ± 30.64
383982 ncm-dbt-04 571391 500 181 69 250 +79.17 ± 14.19 0 17 105 127 1 +165.8 ± 33.35
383981 ncm-dbt-05 583279 500 184 75 241 +76.98 ± 14.13 1 14 111 123 1 +162.35 ± 32.31
383980 ncm-dbt-03 588089 500 192 67 241 +88.74 ± 14.28 0 13 103 130 4 +183.51 ± 33.63
383979 ncm-dbt-01 582778 500 194 81 225 +79.9 ± 13.77 0 13 113 122 2 +165.8 ± 31.92
383978 ncm-dbt-02 587579 500 183 72 245 +78.44 ± 14.46 0 20 99 131 0 +165.8 ± 34.39
383977 ncm-dbt-04 571270 500 182 81 237 +71.16 ± 14.64 1 19 109 120 1 +148.85 ± 32.73
383976 ncm-dbt-05 589882 500 179 78 243 +71.16 ± 14.5 0 18 117 111 4 +142.26 ± 31.44
383975 ncm-dbt-03 583866 500 184 78 238 +74.79 ± 14.63 0 20 106 122 2 +153.86 ± 33.21
383974 ncm-dbt-01 583824 500 185 72 243 +79.9 ± 14.07 0 15 109 124 2 +165.8 ± 32.64
383973 ncm-dbt-02 587367 500 183 73 244 +77.7 ± 14.15 0 17 107 125 1 +162.35 ± 33.02
383972 ncm-dbt-04 571310 500 172 74 254 +68.99 ± 13.86 0 17 119 113 1 +142.26 ± 31.1
383971 ncm-dbt-05 589368 500 179 79 242 +70.43 ± 14.75 0 20 114 112 4 +140.62 ± 31.94
383970 ncm-dbt-03 587579 500 188 71 241 +82.83 ± 14.44 0 16 104 127 3 +171.02 ± 33.51
383969 ncm-dbt-04 572840 500 180 78 242 +71.88 ± 14.39 0 19 112 117 2 +147.19 ± 32.24
383968 ncm-dbt-01 586858 500 177 79 244 +68.99 ± 14.14 0 18 118 112 2 +140.62 ± 31.28
383967 ncm-dbt-02 591512 500 182 74 244 +76.25 ± 14.95 0 20 106 120 4 +153.86 ± 33.21

Commit

Commit ID 0b08953174d222270100690b45fad0dc47c01f98
Author Linmiao Xu
Date 2024-05-13 05:30:18 UTC
Re-evaluate some small net positions for more accurate evals Use main net evals when small net evals hint that higher eval accuracy may be worth the slower eval speeds. With Finny caches, re-evals with the main net are less expensive than before. Original idea by mstembera who I've added as co-author to this PR. Based on reEval tests by mstembera: https://tests.stockfishchess.org/tests/view/65e69187b6345c1b934866e5 https://tests.stockfishchess.org/tests/view/65e863aa0ec64f0526c3e991 A few variants of this patch also passed LTC: https://tests.stockfishchess.org/tests/view/663d2108507ebe1c0e91f407 https://tests.stockfishchess.org/tests/view/663e388c3a2f9702074bc152 Passed STC: https://tests.stockfishchess.org/tests/view/663dadbd1a61d6377f190e2c LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 92320 W: 23941 L: 23531 D: 44848 Ptnml(0-2): 430, 10993, 22931, 11349, 457 Passed LTC: https://tests.stockfishchess.org/tests/view/663ef48b2948bf9aa698690c LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 98934 W: 24907 L: 24457 D: 49570 Ptnml(0-2): 48, 10952, 27027, 11382, 58 closes https://github.com/official-stockfish/Stockfish/pull/5238 bench 1876282 Co-Authored-By: mstembera <5421953+mstembera@users.noreply.github.com>
Copyright 2011–2024 Next Chess Move LLC